BREM-SC is a Bayesian model that jointly clusters single-cell transcriptomic and proteomic data, improving accuracy and quantifying clustering uncertainty.

Nucleic Acids Research · Apr 20, 2020Peer-reviewedGenomics

To improve the predictions of binding residues with DNA, RNA, carbohydrate, and peptide via multiple-task deep neural networks

Zhe Sun, Shuangjia Zheng, Huiying Zhao, Zhangming Niu, Yutong Lu, Yi Feng Pan, Yuedong Yang

The paper introduces MTDsite, a multi-task deep learning method for predicting protein-binding residues across DNA, RNA, peptide, and carbohydrate, achieving higher accuracy than existing methods.

bioRxiv · Feb 11, 2020 · PreprintBioinformatics

Synaptic Proteome Alterations in the Primary Auditory Cortex of Schizophrenia

Matthew L. MacDonald, Megan E. Garver, Jason T. Newman, Zhe Sun, Joseph T. Kannarkat, Ryan B. Salisbury, Jill R. Glausier, Ying Ding, David A. Lewis, Nathan A. Yates, Robert A. Sweet

This study identifies synaptic proteome alterations in the primary auditory cortex of schizophrenia patients, showing coordinated changes in postsynaptic proteins not explained by global protein levels or confounding factors.

bioRxiv · May 16, 2019 · PreprintNeuroscience

BAMM-SC: A Bayesian mixture model for clustering droplet-based single cell transcriptomic data from population studies

Zhe Sun, Li Chen, Hongyi Xin, Yale Jiang, Qianhui Huang, Anthony Richard Cillo, Tracy Tabib, Jay K. Kolls, Tullia Carmela Bruno, Robert Lafyatis, Dario A.A. Vignali, Kong Chen, Ying Ding, Ming Hu, Wei Chen

BAMM-SC clusters droplet-based scRNA-seq data from multiple individuals by accounting for batch effects and heterogeneity, improving accuracy over existing methods.

Nature Communications · Apr 9, 2019Peer-reviewedBioinformatics